Unverified50% confidenceFactExact time
attest's field-role inference relies on field naming conventions, and when an attacker controls the wrapper they can name the result field description; the rule can emit the correct signal but cannot make the input trustworthy.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
Partially VerifiedPrompt injection refers to an attacker embedding malicious instructions into text that the model will read, causing the model to mistake these instructions for part of a legitimate task and execute them.73% similarUnverifiedPrompt injection can be divided into two types: direct injection and indirect injection, where indirect injection refers to attackers hiding malicious instructions in external content read by the agent.69% similarUnverifiedResults from sub-agents are now presented with a header marked as sub-agent output and displayed with indentation, preventing their text from being mistakenly executed as session instructions.69% similarUnverifiedThe writable field set mechanism separately declares which fields are writable, and writes beyond the declared set should be rejected outright rather than truncated.68% similarUnverifiedIn adversarial input scenarios, both typed and generative judges read the content being scored, and the content may carry instructions targeting the judge, so written reasoning cannot reliably expose prompt injection.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057941API
curl https://kongchang.com/api/v1/knowledge/claims/1057941MCP
get_claim(id=1057941)